GPT-5.4 nano: API Pricing, Context Window & Benchmarks
GPT-5.4 nano is a language model from OpenAI, released in March 2026, with multimodal input, a 400K-token context window, and pricing from $0.200/M input and $1.25/M output.
GPT-5.4 nano is OpenAI's cheapest GPT-5.4-class model for simple high-volume tasks. It is optimized for classification, data extraction, ranking, and lightweight coding subagents, while preserving strong reasoning, multimodal
GPT-5.4 nano benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for GPT-5.4 nano across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How GPT-5.4 nano holds up as conversations get longer.
Quality Tracker
GPT-5.4 nano Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sun Sep 06 2026GPT-5.4 nano pricing
Providers
GPT-5.4 nano starts at $0.200 per million input tokens and $1.25 per million output tokens via OpenAI.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 OpenAI | $0.200 | — | $1.25 | 400.0K/128.0K | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
GPT-5.4 nano context window
Input and output token limits for GPT-5.4 nano, plus how it ranks on long-context understanding.
GPT-5.4 nano API
Run a request to see the response
Use it in your code
Billed at $0.20 input / $1.25 output per 1M tokens through the LLM Stats gateway.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://gateway.llm-stats.com/v1"
)
response = client.chat.completions.create(
model="gpt-5.4-nano",
messages=[
{"role": "user", "content": "What is machine learning?"}
]
)
print(response.choices[0].message.content)Need an API key? Create one above in the playground, or read the API documentation.
GPT-5.4 nano latency
GPT-5.4 nano time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
GPT-5.4 nano examples
Recent arena outputs from GPT-5.4 nano, picked from the highest-ranked matchups.
GPT-5.4 nano license
GPT-5.4 nano is a proprietary model available under its provider's product and API terms, has a knowledge cutoff of August 2025.
- License
- Proprietary
- Hosted access
- Knowledge cutoff
- August 2025
Proprietary license - usage restrictions apply
GPT-5.4 nano resources
Official sources for GPT-5.4 nano: api documentation, official playground, official launch post.
GPT-5.4 nano vs other models
The most-compared alternatives to GPT-5.4 nano are Nova 2 Pro, Qwen3 VL 235B A22B Instruct, Qwen3 VL 32B Thinking. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like GPT-5.4 nano
Models ranked just above and below GPT-5.4 nano by LLM Stats score.
FAQ
Common questions about GPT-5.4 nano.